Merge pull request #102 from QwenLM/feature/fan/fix-token-usage
fix: streaming token usage
This commit is contained in:
commit
b8e2891f3b
1 changed files with 1 additions and 0 deletions
|
|
@ -300,6 +300,7 @@ export class OpenAIContentGenerator implements ContentGenerator {
|
|||
messages,
|
||||
...samplingParams,
|
||||
stream: true,
|
||||
stream_options: { include_usage: true },
|
||||
};
|
||||
|
||||
if (request.config?.tools) {
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue